install packages

if(!require('sf'))install.packages('sf')
if(!require('raster'))install.packages('raster')
if(!require('dplyr'))install.packages('dplyr')
if(!require('spData'))install.packages('spData')
library(sf)
library(raster)
library(dplyr)
library(spData)
if(!require('spDataLarge'))install.packages("spDataLarge", repos = "https://nowosad.github.io/drat/", type = "source")
library(spDataLarge)
library(tmap)
library(leaflet)
library(mapview)
library(ggplot2)
library(shiny)

load dataset

if(!require('rgdal'))install.packages('rgdal')
library(rgdal)
shp <- readOGR(".", 'tract_crime')
OGR data source with driver: ESRI Shapefile 
Source: "C:\GEOG533\GEOG-533\Final_Project", layer: "tract_crime"
with 148 features
It has 101 fields
Integer64 fields read as strings:  B02001e2 B02001e3 B00001e1 B23003e1 C17002e1 B15003e22 B19013e1 B25001e1 B25004e1 B25077e1 Rowid_ ZONE_CODE COUNT Rowid1 ZONE_COD_1 COUNT_1 
if(!require('tmap'))install.packages('tmap')
library(tmap)
df <- shp@data
tract <- shp

The distribution of crimes

map_tract <- tm_shape(tract,name = 'X2018_Murde') + tm_polygons('X2018_Murde')+tm_shape(tract,name = 'X2018_Motor') + tm_polygons('X2018_Motor')+tm_shape(tract,name = 'X2018_Larce') + tm_polygons('X2018_Larce')+tm_shape(tract,name = 'X2018_Prope') + tm_polygons('X2018_Prope')+tm_shape(tract,name = 'X2018_Rape') + tm_polygons('X2018_Rape')
tmap_mode('view')
tmap mode set to interactive viewing
map_tract

Regression

sub_df <- df[,c('Mean_NTL',"X2018_Murde","Pop_Dens_1","Employ_R_1","Poverty__1","Educatio_1","Median_I_1","House_De_1","Vacant_R_1","House_Va_1","Room_Num_1","X2018_Motor","X2018_Larce","X2018_Prope","X2018_Rape","X2018_Murde")]
sub_df
library(car)
full.model <- lm(sub_df$X2018_Murde.1 ~sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1)
reduced.model <- step(full.model, direction = 'backward')
Start:  AIC=1396.79
sub_df$X2018_Murde.1 ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + 
    sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + 
    sub_df$House_Va_1 + sub_df$Room_Num_1

                    Df Sum of Sq     RSS    AIC
- sub_df$House_De_1  1      4649 1605966 1395.2
- sub_df$House_Va_1  1      8349 1609665 1395.6
<none>                           1601316 1396.8
- sub_df$Vacant_R_1  1     36966 1638282 1398.2
- sub_df$Poverty__1  1     50366 1651682 1399.4
- sub_df$Employ_R_1  1    103504 1704820 1404.1
- sub_df$Pop_Dens_1  1    110474 1711791 1404.7
- sub_df$Educatio_1  1    150665 1751982 1408.1
- sub_df$Median_I_1  1    186520 1787836 1411.1
- sub_df$Room_Num_1  1    247568 1848884 1416.1
- sub_df$Mean_NTL    1    533447 2134763 1437.3

Step:  AIC=1395.22
sub_df$X2018_Murde.1 ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + 
    sub_df$Median_I_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq     RSS    AIC
- sub_df$House_Va_1  1     12100 1618066 1394.3
<none>                           1605966 1395.2
- sub_df$Vacant_R_1  1     32868 1638834 1396.2
- sub_df$Poverty__1  1     46712 1652678 1397.5
- sub_df$Employ_R_1  1    103232 1709197 1402.4
- sub_df$Pop_Dens_1  1    140202 1746168 1405.6
- sub_df$Educatio_1  1    151193 1757158 1406.5
- sub_df$Median_I_1  1    192285 1798251 1410.0
- sub_df$Room_Num_1  1    243340 1849305 1414.1
- sub_df$Mean_NTL    1    565638 2171603 1437.9

Step:  AIC=1394.33
sub_df$X2018_Murde.1 ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + 
    sub_df$Median_I_1 + sub_df$Vacant_R_1 + sub_df$Room_Num_1

                    Df Sum of Sq     RSS    AIC
<none>                           1618066 1394.3
- sub_df$Vacant_R_1  1     35808 1653874 1395.6
- sub_df$Poverty__1  1     40946 1659012 1396.0
- sub_df$Employ_R_1  1     94801 1712867 1400.8
- sub_df$Pop_Dens_1  1    135438 1753504 1404.2
- sub_df$Educatio_1  1    141551 1759617 1404.7
- sub_df$Median_I_1  1    221933 1839999 1411.3
- sub_df$Room_Num_1  1    251779 1869845 1413.7
- sub_df$Mean_NTL    1    748308 2366374 1448.6
reduced.model

Call:
lm(formula = sub_df$X2018_Murde.1 ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + 
    sub_df$Median_I_1 + sub_df$Vacant_R_1 + sub_df$Room_Num_1)

Coefficients:
      (Intercept)    sub_df$Mean_NTL  sub_df$Pop_Dens_1  
       -296.00388            4.12917           -0.53812  
sub_df$Employ_R_1  sub_df$Poverty__1  sub_df$Educatio_1  
         50.41677          -11.31568          -39.52070  
sub_df$Median_I_1  sub_df$Vacant_R_1  sub_df$Room_Num_1  
         -0.00346          327.33486           87.60889  
full.model <- lm(sub_df$X2018_Rape~sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1)
reduced.model <- step(full.model, direction = 'backward')
Start:  AIC=1312.12
sub_df$X2018_Rape ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Mean_NTL    1     293.4 903986 1310.2
- sub_df$Room_Num_1  1    3144.1 906836 1310.6
- sub_df$Educatio_1  1    6511.2 910203 1311.2
- sub_df$House_Va_1  1    8232.3 911925 1311.5
<none>                           903692 1312.1
- sub_df$Median_I_1  1   13927.9 917620 1312.4
- sub_df$Vacant_R_1  1   14056.9 917749 1312.4
- sub_df$Poverty__1  1   14631.6 918324 1312.5
- sub_df$Employ_R_1  1   17481.4 921174 1313.0
- sub_df$Pop_Dens_1  1   22732.0 926424 1313.8
- sub_df$House_De_1  1   23170.2 926862 1313.9

Step:  AIC=1310.17
sub_df$X2018_Rape ~ sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + 
    sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + 
    sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Room_Num_1  1    4049.4 908035 1308.8
- sub_df$Educatio_1  1    6598.9 910585 1309.2
- sub_df$House_Va_1  1   10533.2 914519 1309.9
<none>                           903986 1310.2
- sub_df$Median_I_1  1   13673.9 917660 1310.4
- sub_df$Vacant_R_1  1   13765.5 917751 1310.4
- sub_df$Poverty__1  1   14347.9 918334 1310.5
- sub_df$Employ_R_1  1   17400.2 921386 1311.0
- sub_df$House_De_1  1   22944.4 926930 1311.9
- sub_df$Pop_Dens_1  1   24473.7 928459 1312.1

Step:  AIC=1308.83
sub_df$X2018_Rape ~ sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + 
    sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + 
    sub_df$Vacant_R_1 + sub_df$House_Va_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Educatio_1  1    9332.8 917368 1308.3
- sub_df$Median_I_1  1    9769.3 917804 1308.4
- sub_df$Vacant_R_1  1   10212.7 918248 1308.5
- sub_df$House_Va_1  1   10421.1 918456 1308.5
- sub_df$Poverty__1  1   11260.3 919295 1308.7
<none>                           908035 1308.8
- sub_df$Employ_R_1  1   14393.1 922428 1309.2
- sub_df$House_De_1  1   19700.0 927735 1310.0
- sub_df$Pop_Dens_1  1   24906.8 932942 1310.8

Step:  AIC=1308.34
sub_df$X2018_Rape ~ sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + 
    sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + 
    sub_df$House_Va_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Employ_R_1  1    6223.9 923592 1307.3
- sub_df$Poverty__1  1    6651.1 924019 1307.4
- sub_df$Vacant_R_1  1   10786.3 928154 1308.1
<none>                           917368 1308.3
- sub_df$House_Va_1  1   14680.9 932049 1308.7
- sub_df$Median_I_1  1   16574.8 933943 1309.0
- sub_df$House_De_1  1   18484.0 935852 1309.3
- sub_df$Pop_Dens_1  1   24285.2 941653 1310.2

Step:  AIC=1307.34
sub_df$X2018_Rape ~ sub_df$Pop_Dens_1 + sub_df$Poverty__1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Poverty__1  1     479.6 924071 1305.4
- sub_df$Vacant_R_1  1   11977.0 935569 1307.2
<none>                           923592 1307.3
- sub_df$Median_I_1  1   13944.3 937536 1307.6
- sub_df$House_Va_1  1   16182.9 939775 1307.9
- sub_df$House_De_1  1   21024.2 944616 1308.7
- sub_df$Pop_Dens_1  1   23432.8 947025 1309.0

Step:  AIC=1305.42
sub_df$X2018_Rape ~ sub_df$Pop_Dens_1 + sub_df$Median_I_1 + sub_df$House_De_1 + 
    sub_df$Vacant_R_1 + sub_df$House_Va_1

                    Df Sum of Sq    RSS    AIC
<none>                           924071 1305.4
- sub_df$Vacant_R_1  1     12750 936822 1305.5
- sub_df$Median_I_1  1     14139 938210 1305.7
- sub_df$House_Va_1  1     15727 939798 1305.9
- sub_df$House_De_1  1     23978 948049 1307.2
- sub_df$Pop_Dens_1  1     29295 953367 1308.0
reduced.model

Call:
lm(formula = sub_df$X2018_Rape ~ sub_df$Pop_Dens_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1)

Coefficients:
      (Intercept)  sub_df$Pop_Dens_1  sub_df$Median_I_1  
        2.324e+02         -2.622e-01         -8.125e-04  
sub_df$House_De_1  sub_df$Vacant_R_1  sub_df$House_Va_1  
        5.398e-02          1.840e+02         -1.589e-04  
full.model <- lm(sub_df$X2018_Prope~sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1)
reduced.model <- step(full.model, direction = 'backward')
Start:  AIC=1071.99
sub_df$X2018_Prope ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Median_I_1  1        10 178402 1070.0
- sub_df$Vacant_R_1  1        58 178450 1070.0
- sub_df$Educatio_1  1       181 178573 1070.1
- sub_df$House_Va_1  1      1383 179775 1071.1
<none>                           178392 1072.0
- sub_df$Employ_R_1  1      8984 187376 1077.3
- sub_df$House_De_1  1     11887 190279 1079.5
- sub_df$Poverty__1  1     14435 192827 1081.5
- sub_df$Room_Num_1  1     14558 192950 1081.6
- sub_df$Pop_Dens_1  1     39829 218221 1099.8
- sub_df$Mean_NTL    1    185412 363804 1175.5

Step:  AIC=1070
sub_df$X2018_Prope ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$House_De_1 + 
    sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Vacant_R_1  1        60 178462 1068.0
- sub_df$Educatio_1  1       173 178575 1068.1
<none>                           178402 1070.0
- sub_df$House_Va_1  1      2473 180875 1070.0
- sub_df$Employ_R_1  1      9063 187465 1075.3
- sub_df$House_De_1  1     11906 190308 1077.6
- sub_df$Poverty__1  1     15040 193442 1080.0
- sub_df$Room_Num_1  1     20818 199220 1084.3
- sub_df$Pop_Dens_1  1     39986 218388 1097.9
- sub_df$Mean_NTL    1    193486 371888 1176.7

Step:  AIC=1068.05
sub_df$X2018_Prope ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$House_De_1 + 
    sub_df$House_Va_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Educatio_1  1       195 178657 1066.2
<none>                           178462 1068.0
- sub_df$House_Va_1  1      2699 181160 1068.3
- sub_df$Employ_R_1  1      9101 187563 1073.4
- sub_df$House_De_1  1     12206 190668 1075.8
- sub_df$Poverty__1  1     15068 193530 1078.0
- sub_df$Room_Num_1  1     22733 201194 1083.8
- sub_df$Pop_Dens_1  1     41549 220011 1097.0
- sub_df$Mean_NTL    1    195825 374286 1175.7

Step:  AIC=1066.21
sub_df$X2018_Prope ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$House_De_1 + sub_df$House_Va_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
<none>                           178657 1066.2
- sub_df$House_Va_1  1      2651 181308 1066.4
- sub_df$House_De_1  1     12253 190909 1074.0
- sub_df$Employ_R_1  1     16012 194669 1076.9
- sub_df$Poverty__1  1     17894 196551 1078.3
- sub_df$Room_Num_1  1     22675 201332 1081.9
- sub_df$Pop_Dens_1  1     41764 220421 1095.3
- sub_df$Mean_NTL    1    195709 374366 1173.7
reduced.model

Call:
lm(formula = sub_df$X2018_Prope ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$House_De_1 + 
    sub_df$House_Va_1 + sub_df$Room_Num_1)

Coefficients:
      (Intercept)    sub_df$Mean_NTL  sub_df$Pop_Dens_1  
        2.505e+02          2.261e+00         -3.823e-01  
sub_df$Employ_R_1  sub_df$Poverty__1  sub_df$House_De_1  
        1.699e+01         -7.092e+00         -4.535e-02  
sub_df$House_Va_1  sub_df$Room_Num_1  
       -4.859e-05         -2.133e+01  
full.model <- lm(sub_df$X2018_Larce ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1)
reduced.model <- step(full.model, direction = 'backward')
Start:  AIC=1107.98
sub_df$X2018_Larce ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Vacant_R_1  1         1 227497 1106.0
- sub_df$Median_I_1  1      1611 229107 1107.0
- sub_df$House_Va_1  1      2445 229941 1107.6
<none>                           227496 1108.0
- sub_df$Educatio_1  1      3516 231012 1108.2
- sub_df$Employ_R_1  1      7685 235181 1110.9
- sub_df$Poverty__1  1     16615 244111 1116.4
- sub_df$House_De_1  1     32946 260442 1126.0
- sub_df$Room_Num_1  1     33898 261394 1126.5
- sub_df$Pop_Dens_1  1     43022 270518 1131.6
- sub_df$Mean_NTL    1    230404 457900 1209.5

Step:  AIC=1105.98
sub_df$X2018_Larce ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$House_Va_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Median_I_1  1      1616 229113 1105.0
- sub_df$House_Va_1  1      2467 229964 1105.6
<none>                           227497 1106.0
- sub_df$Educatio_1  1      3541 231039 1106.3
- sub_df$Employ_R_1  1      7685 235183 1108.9
- sub_df$Poverty__1  1     16616 244113 1114.4
- sub_df$House_De_1  1     34989 262487 1125.2
- sub_df$Room_Num_1  1     37626 265123 1126.6
- sub_df$Pop_Dens_1  1     44050 271547 1130.2
- sub_df$Mean_NTL    1    234660 462157 1208.9

Step:  AIC=1105.02
sub_df$X2018_Larce ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$House_De_1 + 
    sub_df$House_Va_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$House_Va_1  1       987 230101 1103.7
<none>                           229113 1105.0
- sub_df$Educatio_1  1      5924 235037 1106.8
- sub_df$Employ_R_1  1      8789 237902 1108.6
- sub_df$Poverty__1  1     20084 249197 1115.5
- sub_df$House_De_1  1     36623 265736 1125.0
- sub_df$Room_Num_1  1     42176 271289 1128.0
- sub_df$Pop_Dens_1  1     43254 272367 1128.6
- sub_df$Mean_NTL    1    236075 465188 1207.8

Step:  AIC=1103.66
sub_df$X2018_Larce ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$House_De_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
<none>                           230101 1103.7
- sub_df$Educatio_1  1      4971 235071 1104.8
- sub_df$Employ_R_1  1      9436 239536 1107.6
- sub_df$Poverty__1  1     19691 249791 1113.8
- sub_df$House_De_1  1     40637 270738 1125.7
- sub_df$Pop_Dens_1  1     42643 272743 1126.8
- sub_df$Room_Num_1  1     84881 314981 1148.1
- sub_df$Mean_NTL    1    251144 481245 1210.9
reduced.model

Call:
lm(formula = sub_df$X2018_Larce ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + 
    sub_df$House_De_1 + sub_df$Room_Num_1)

Coefficients:
      (Intercept)    sub_df$Mean_NTL  sub_df$Pop_Dens_1  
        309.98116            2.43673           -0.38584  
sub_df$Employ_R_1  sub_df$Poverty__1  sub_df$Educatio_1  
         15.88780           -7.81962            6.19976  
sub_df$House_De_1  sub_df$Room_Num_1  
         -0.08095          -31.90863  
full.model <- lm(sub_df$X2018_Motor ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + sub_df$Room_Num_1)
reduced.model <- step(full.model, direction = 'backward')
Start:  AIC=1104.45
sub_df$X2018_Motor ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$House_Va_1 + 
    sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$House_Va_1  1       110 222246 1102.5
- sub_df$House_De_1  1       120 222255 1102.5
- sub_df$Room_Num_1  1       530 222665 1102.8
- sub_df$Median_I_1  1      1370 223505 1103.4
<none>                           222135 1104.5
- sub_df$Educatio_1  1      3420 225555 1104.7
- sub_df$Employ_R_1  1      3554 225690 1104.8
- sub_df$Poverty__1  1      4249 226384 1105.2
- sub_df$Vacant_R_1  1      7507 229642 1107.4
- sub_df$Pop_Dens_1  1     29271 251406 1120.8
- sub_df$Mean_NTL    1    121178 343313 1166.9

Step:  AIC=1102.52
sub_df$X2018_Motor ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$House_De_1 + sub_df$Vacant_R_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$House_De_1  1       189 222434 1100.7
- sub_df$Room_Num_1  1       588 222834 1100.9
<none>                           222246 1102.5
- sub_df$Median_I_1  1      3053 225299 1102.5
- sub_df$Educatio_1  1      3702 225947 1103.0
- sub_df$Employ_R_1  1      3832 226078 1103.0
- sub_df$Poverty__1  1      4433 226679 1103.4
- sub_df$Vacant_R_1  1      7834 230080 1105.7
- sub_df$Pop_Dens_1  1     29198 251444 1118.8
- sub_df$Mean_NTL    1    134156 356401 1170.4

Step:  AIC=1100.65
sub_df$X2018_Motor ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$Vacant_R_1 + sub_df$Room_Num_1

                    Df Sum of Sq    RSS    AIC
- sub_df$Room_Num_1  1       500 222934 1099.0
<none>                           222434 1100.7
- sub_df$Median_I_1  1      3204 225638 1100.8
- sub_df$Educatio_1  1      3750 226184 1101.1
- sub_df$Employ_R_1  1      3912 226346 1101.2
- sub_df$Poverty__1  1      4985 227419 1101.9
- sub_df$Vacant_R_1  1      7676 230110 1103.7
- sub_df$Pop_Dens_1  1     53841 276276 1130.7
- sub_df$Mean_NTL    1    141529 363964 1171.5

Step:  AIC=1098.98
sub_df$X2018_Motor ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + sub_df$Employ_R_1 + 
    sub_df$Poverty__1 + sub_df$Educatio_1 + sub_df$Median_I_1 + 
    sub_df$Vacant_R_1

                    Df Sum of Sq    RSS    AIC
<none>                           222934 1099.0
- sub_df$Educatio_1  1      3376 226311 1099.2
- sub_df$Employ_R_1  1      4928 227862 1100.2
- sub_df$Poverty__1  1      6029 228963 1100.9
- sub_df$Vacant_R_1  1      7180 230114 1101.7
- sub_df$Median_I_1  1     12771 235706 1105.2
- sub_df$Pop_Dens_1  1     53344 276278 1128.7
- sub_df$Mean_NTL    1    164534 387468 1178.8
reduced.model

Call:
lm(formula = sub_df$X2018_Motor ~ sub_df$Mean_NTL + sub_df$Pop_Dens_1 + 
    sub_df$Employ_R_1 + sub_df$Poverty__1 + sub_df$Educatio_1 + 
    sub_df$Median_I_1 + sub_df$Vacant_R_1)

Coefficients:
      (Intercept)    sub_df$Mean_NTL  sub_df$Pop_Dens_1  
        1.042e+02          1.831e+00         -3.359e-01  
sub_df$Employ_R_1  sub_df$Poverty__1  sub_df$Educatio_1  
        1.114e+01         -4.230e+00         -5.999e+00  
sub_df$Median_I_1  sub_df$Vacant_R_1  
       -5.404e-04         -1.409e+02  
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